Chunk alignment for the bilingual corpus is the base of Example-based Machine Translation. An anchor-based English-Chinese bilingual chunk alignment model and the corresponding algorithm of alignment are presented in ...Chunk alignment for the bilingual corpus is the base of Example-based Machine Translation. An anchor-based English-Chinese bilingual chunk alignment model and the corresponding algorithm of alignment are presented in this paper. It can effectively overcome the sparse data problem due to the limited size of the bilingual corpus. In this model, the chunk segmentation disarnbiguation is delayed to the alignment process, and hence the accuracy of chunk segmentation is improved. The experimental results demonstrate the feasibility and viability of this model.展开更多
On-line assessment of English-Chinese translation is a challenging task as it involves natural language processing.YanFa,an on-line assessment system for English-Chinese translation,is a pilot research project into sc...On-line assessment of English-Chinese translation is a challenging task as it involves natural language processing.YanFa,an on-line assessment system for English-Chinese translation,is a pilot research project into scoring student's translation on-line.Based on the theory of translation equivalence,an algorithm called "conceptual similarity matching" was developed.YanFa can assess students' translation on-line timely,generate test papers automatically,offer standard versions of translation,and the scores of each sentence to students.The evaluation proves that YanFa is practical compared with the scores given by experts.展开更多
文摘Chunk alignment for the bilingual corpus is the base of Example-based Machine Translation. An anchor-based English-Chinese bilingual chunk alignment model and the corresponding algorithm of alignment are presented in this paper. It can effectively overcome the sparse data problem due to the limited size of the bilingual corpus. In this model, the chunk segmentation disarnbiguation is delayed to the alignment process, and hence the accuracy of chunk segmentation is improved. The experimental results demonstrate the feasibility and viability of this model.
基金The National Natural Science Foundation ofChina(No.60496326)
文摘On-line assessment of English-Chinese translation is a challenging task as it involves natural language processing.YanFa,an on-line assessment system for English-Chinese translation,is a pilot research project into scoring student's translation on-line.Based on the theory of translation equivalence,an algorithm called "conceptual similarity matching" was developed.YanFa can assess students' translation on-line timely,generate test papers automatically,offer standard versions of translation,and the scores of each sentence to students.The evaluation proves that YanFa is practical compared with the scores given by experts.
